GPTQ Version of meta-llama/Llama-3.2-1B: 8 bit, 128 groupsize
✅ Tested on vLLM

Downloads last month
601
Safetensors
Model size
516M params
Tensor type
I32
·
FP16
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for adriabama06/Llama-3.2-1B-Instruct-GPTQ-8bit-128g

Quantized
(187)
this model